AAAI 2025 paper

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning

25citations

25

Citations

#72

in AAAI 2025

of 3028 papers

6

Authors

1

Data Points

Authors

Xin Yi Shunfan Zheng Linlin Wang Gerard de Melo Xiaoling Wang Liang He

Citation History

Jan 28, 2026

25